summaryrefslogtreecommitdiffstats
path: root/drivers/vfio/group.c
blob: bb24b2f0271e03c3b1a027b0ef8e717951f157ab (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VFIO core
 *
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * Derived from original vfio:
 * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
 * Author: Tom Lyon, pugs@cisco.com
 */

#include <linux/vfio.h>
#include <linux/iommufd.h>
#include <linux/anon_inodes.h>
#include "vfio.h"

static struct vfio {
	struct class			*class;
	struct list_head		group_list;
	struct mutex			group_lock; /* locks group_list */
	struct ida			group_ida;
	dev_t				group_devt;
} vfio;

static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
						     char *buf)
{
	struct vfio_device *it, *device = ERR_PTR(-ENODEV);

	mutex_lock(&group->device_lock);
	list_for_each_entry(it, &group->device_list, group_next) {
		int ret;

		if (it->ops->match) {
			ret = it->ops->match(it, buf);
			if (ret < 0) {
				device = ERR_PTR(ret);
				break;
			}
		} else {
			ret = !strcmp(dev_name(it->dev), buf);
		}

		if (ret && vfio_device_try_get_registration(it)) {
			device = it;
			break;
		}
	}
	mutex_unlock(&group->device_lock);

	return device;
}

/*
 * VFIO Group fd, /dev/vfio/$GROUP
 */
static bool vfio_group_has_iommu(struct vfio_group *group)
{
	lockdep_assert_held(&group->group_lock);
	/*
	 * There can only be users if there is a container, and if there is a
	 * container there must be users.
	 */
	WARN_ON(!group->container != !group->container_users);

	return group->container || group->iommufd;
}

/*
 * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
 * if there was no container to unset.  Since the ioctl is called on
 * the group, we know that still exists, therefore the only valid
 * transition here is 1->0.
 */
static int vfio_group_ioctl_unset_container(struct vfio_group *group)
{
	int ret = 0;

	mutex_lock(&group->group_lock);
	if (!vfio_group_has_iommu(group)) {
		ret = -EINVAL;
		goto out_unlock;
	}
	if (group->container) {
		if (group->container_users != 1) {
			ret = -EBUSY;
			goto out_unlock;
		}
		vfio_group_detach_container(group);
	}
	if (group->iommufd) {
		iommufd_ctx_put(group->iommufd);
		group->iommufd = NULL;
	}

out_unlock:
	mutex_unlock(&group->group_lock);
	return ret;
}

static int vfio_group_ioctl_set_container(struct vfio_group *group,
					  int __user *arg)
{
	struct vfio_container *container;
	struct iommufd_ctx *iommufd;
	struct fd f;
	int ret;
	int fd;

	if (get_user(fd, arg))
		return -EFAULT;

	f = fdget(fd);
	if (!f.file)
		return -EBADF;

	mutex_lock(&group->group_lock);
	if (vfio_group_has_iommu(group)) {
		ret = -EINVAL;
		goto out_unlock;
	}
	if (!group->iommu_group) {
		ret = -ENODEV;
		goto out_unlock;
	}

	container = vfio_container_from_file(f.file);
	if (container) {
		ret = vfio_container_attach_group(container, group);
		goto out_unlock;
	}

	iommufd = iommufd_ctx_from_file(f.file);
	if (!IS_ERR(iommufd)) {
		u32 ioas_id;

		ret = iommufd_vfio_compat_ioas_id(iommufd, &ioas_id);
		if (ret) {
			iommufd_ctx_put(group->iommufd);
			goto out_unlock;
		}

		group->iommufd = iommufd;
		goto out_unlock;
	}

	/* The FD passed is not recognized. */
	ret = -EBADFD;

out_unlock:
	mutex_unlock(&group->group_lock);
	fdput(f);
	return ret;
}

static int vfio_device_group_open(struct vfio_device *device)
{
	int ret;

	mutex_lock(&device->group->group_lock);
	if (!vfio_group_has_iommu(device->group)) {
		ret = -EINVAL;
		goto out_unlock;
	}

	/*
	 * Here we pass the KVM pointer with the group under the lock.  If the
	 * device driver will use it, it must obtain a reference and release it
	 * during close_device.
	 */
	ret = vfio_device_open(device, device->group->iommufd,
			       device->group->kvm);

out_unlock:
	mutex_unlock(&device->group->group_lock);
	return ret;
}

void vfio_device_group_close(struct vfio_device *device)
{
	mutex_lock(&device->group->group_lock);
	vfio_device_close(device, device->group->iommufd);
	mutex_unlock(&device->group->group_lock);
}

static struct file *vfio_device_open_file(struct vfio_device *device)
{
	struct file *filep;
	int ret;

	ret = vfio_device_group_open(device);
	if (ret)
		goto err_out;

	/*
	 * We can't use anon_inode_getfd() because we need to modify
	 * the f_mode flags directly to allow more than just ioctls
	 */
	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
				   device, O_RDWR);
	if (IS_ERR(filep)) {
		ret = PTR_ERR(filep);
		goto err_close_device;
	}

	/*
	 * TODO: add an anon_inode interface to do this.
	 * Appears to be missing by lack of need rather than
	 * explicitly prevented.  Now there's need.
	 */
	filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);

	if (device->group->type == VFIO_NO_IOMMU)
		dev_warn(device->dev, "vfio-noiommu device opened by user "
			 "(%s:%d)\n", current->comm, task_pid_nr(current));
	/*
	 * On success the ref of device is moved to the file and
	 * put in vfio_device_fops_release()
	 */
	return filep;

err_close_device:
	vfio_device_group_close(device);
err_out:
	return ERR_PTR(ret);
}

static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
					  char __user *arg)
{
	struct vfio_device *device;
	struct file *filep;
	char *buf;
	int fdno;
	int ret;

	buf = strndup_user(arg, PAGE_SIZE);
	if (IS_ERR(buf))
		return PTR_ERR(buf);

	device = vfio_device_get_from_name(group, buf);
	kfree(buf);
	if (IS_ERR(device))
		return PTR_ERR(device);

	fdno = get_unused_fd_flags(O_CLOEXEC);
	if (fdno < 0) {
		ret = fdno;
		goto err_put_device;
	}

	filep = vfio_device_open_file(device);
	if (IS_ERR(filep)) {
		ret = PTR_ERR(filep);
		goto err_put_fdno;
	}

	fd_install(fdno, filep);
	return fdno;

err_put_fdno:
	put_unused_fd(fdno);
err_put_device:
	vfio_device_put_registration(device);
	return ret;
}

static int vfio_group_ioctl_get_status(struct vfio_group *group,
				       struct vfio_group_status __user *arg)
{
	unsigned long minsz = offsetofend(struct vfio_group_status, flags);
	struct vfio_group_status status;

	if (copy_from_user(&status, arg, minsz))
		return -EFAULT;

	if (status.argsz < minsz)
		return -EINVAL;

	status.flags = 0;

	mutex_lock(&group->group_lock);
	if (!group->iommu_group) {
		mutex_unlock(&group->group_lock);
		return -ENODEV;
	}

	/*
	 * With the container FD the iommu_group_claim_dma_owner() is done
	 * during SET_CONTAINER but for IOMMFD this is done during
	 * VFIO_GROUP_GET_DEVICE_FD. Meaning that with iommufd
	 * VFIO_GROUP_FLAGS_VIABLE could be set but GET_DEVICE_FD will fail due
	 * to viability.
	 */
	if (vfio_group_has_iommu(group))
		status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
				VFIO_GROUP_FLAGS_VIABLE;
	else if (!iommu_group_dma_owner_claimed(group->iommu_group))
		status.flags |= VFIO_GROUP_FLAGS_VIABLE;
	mutex_unlock(&group->group_lock);

	if (copy_to_user(arg, &status, minsz))
		return -EFAULT;
	return 0;
}

static long vfio_group_fops_unl_ioctl(struct file *filep,
				      unsigned int cmd, unsigned long arg)
{
	struct vfio_group *group = filep->private_data;
	void __user *uarg = (void __user *)arg;

	switch (cmd) {
	case VFIO_GROUP_GET_DEVICE_FD:
		return vfio_group_ioctl_get_device_fd(group, uarg);
	case VFIO_GROUP_GET_STATUS:
		return vfio_group_ioctl_get_status(group, uarg);
	case VFIO_GROUP_SET_CONTAINER:
		return vfio_group_ioctl_set_container(group, uarg);
	case VFIO_GROUP_UNSET_CONTAINER:
		return vfio_group_ioctl_unset_container(group);
	default:
		return -ENOTTY;
	}
}

static int vfio_group_fops_open(struct inode *inode, struct file *filep)
{
	struct vfio_group *group =
		container_of(inode->i_cdev, struct vfio_group, cdev);
	int ret;

	mutex_lock(&group->group_lock);

	/*
	 * drivers can be zero if this races with vfio_device_remove_group(), it
	 * will be stable at 0 under the group rwsem
	 */
	if (refcount_read(&group->drivers) == 0) {
		ret = -ENODEV;
		goto out_unlock;
	}

	if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
		ret = -EPERM;
		goto out_unlock;
	}

	/*
	 * Do we need multiple instances of the group open?  Seems not.
	 */
	if (group->opened_file) {
		ret = -EBUSY;
		goto out_unlock;
	}
	group->opened_file = filep;
	filep->private_data = group;
	ret = 0;
out_unlock:
	mutex_unlock(&group->group_lock);
	return ret;
}

static int vfio_group_fops_release(struct inode *inode, struct file *filep)
{
	struct vfio_group *group = filep->private_data;

	filep->private_data = NULL;

	mutex_lock(&group->group_lock);
	/*
	 * Device FDs hold a group file reference, therefore the group release
	 * is only called when there are no open devices.
	 */
	WARN_ON(group->notifier.head);
	if (group->container)
		vfio_group_detach_container(group);
	if (group->iommufd) {
		iommufd_ctx_put(group->iommufd);
		group->iommufd = NULL;
	}
	group->opened_file = NULL;
	mutex_unlock(&group->group_lock);
	return 0;
}

static const struct file_operations vfio_group_fops = {
	.owner		= THIS_MODULE,
	.unlocked_ioctl	= vfio_group_fops_unl_ioctl,
	.compat_ioctl	= compat_ptr_ioctl,
	.open		= vfio_group_fops_open,
	.release	= vfio_group_fops_release,
};

/*
 * Group objects - create, release, get, put, search
 */
static struct vfio_group *
vfio_group_find_from_iommu(struct iommu_group *iommu_group)
{
	struct vfio_group *group;

	lockdep_assert_held(&vfio.group_lock);

	/*
	 * group->iommu_group from the vfio.group_list cannot be NULL
	 * under the vfio.group_lock.
	 */
	list_for_each_entry(group, &vfio.group_list, vfio_next) {
		if (group->iommu_group == iommu_group)
			return group;
	}
	return NULL;
}

static void vfio_group_release(struct device *dev)
{
	struct vfio_group *group = container_of(dev, struct vfio_group, dev);

	mutex_destroy(&group->device_lock);
	mutex_destroy(&group->group_lock);
	WARN_ON(group->iommu_group);
	ida_free(&vfio.group_ida, MINOR(group->dev.devt));
	kfree(group);
}

static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
					   enum vfio_group_type type)
{
	struct vfio_group *group;
	int minor;

	group = kzalloc(sizeof(*group), GFP_KERNEL);
	if (!group)
		return ERR_PTR(-ENOMEM);

	minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
	if (minor < 0) {
		kfree(group);
		return ERR_PTR(minor);
	}

	device_initialize(&group->dev);
	group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
	group->dev.class = vfio.class;
	group->dev.release = vfio_group_release;
	cdev_init(&group->cdev, &vfio_group_fops);
	group->cdev.owner = THIS_MODULE;

	refcount_set(&group->drivers, 1);
	mutex_init(&group->group_lock);
	INIT_LIST_HEAD(&group->device_list);
	mutex_init(&group->device_lock);
	group->iommu_group = iommu_group;
	/* put in vfio_group_release() */
	iommu_group_ref_get(iommu_group);
	group->type = type;
	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);

	return group;
}

static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
		enum vfio_group_type type)
{
	struct vfio_group *group;
	struct vfio_group *ret;
	int err;

	lockdep_assert_held(&vfio.group_lock);

	group = vfio_group_alloc(iommu_group, type);
	if (IS_ERR(group))
		return group;

	err = dev_set_name(&group->dev, "%s%d",
			   group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
			   iommu_group_id(iommu_group));
	if (err) {
		ret = ERR_PTR(err);
		goto err_put;
	}

	err = cdev_device_add(&group->cdev, &group->dev);
	if (err) {
		ret = ERR_PTR(err);
		goto err_put;
	}

	list_add(&group->vfio_next, &vfio.group_list);

	return group;

err_put:
	put_device(&group->dev);
	return ret;
}

static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
		enum vfio_group_type type)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;
	int ret;

	iommu_group = iommu_group_alloc();
	if (IS_ERR(iommu_group))
		return ERR_CAST(iommu_group);

	ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
	if (ret)
		goto out_put_group;
	ret = iommu_group_add_device(iommu_group, dev);
	if (ret)
		goto out_put_group;

	mutex_lock(&vfio.group_lock);
	group = vfio_create_group(iommu_group, type);
	mutex_unlock(&vfio.group_lock);
	if (IS_ERR(group)) {
		ret = PTR_ERR(group);
		goto out_remove_device;
	}
	iommu_group_put(iommu_group);
	return group;

out_remove_device:
	iommu_group_remove_device(dev);
out_put_group:
	iommu_group_put(iommu_group);
	return ERR_PTR(ret);
}

static bool vfio_group_has_device(struct vfio_group *group, struct device *dev)
{
	struct vfio_device *device;

	mutex_lock(&group->device_lock);
	list_for_each_entry(device, &group->device_list, group_next) {
		if (device->dev == dev) {
			mutex_unlock(&group->device_lock);
			return true;
		}
	}
	mutex_unlock(&group->device_lock);
	return false;
}

static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
{
	struct iommu_group *iommu_group;
	struct vfio_group *group;

	iommu_group = iommu_group_get(dev);
	if (!iommu_group && vfio_noiommu) {
		/*
		 * With noiommu enabled, create an IOMMU group for devices that
		 * don't already have one, implying no IOMMU hardware/driver
		 * exists.  Taint the kernel because we're about to give a DMA
		 * capable device to a user without IOMMU protection.
		 */
		group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
		if (!IS_ERR(group)) {
			add_taint(TAINT_USER, LOCKDEP_STILL_OK);
			dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
		}
		return group;
	}

	if (!iommu_group)
		return ERR_PTR(-EINVAL);

	/*
	 * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
	 * restore cache coherency. It has to be checked here because it is only
	 * valid for cases where we are using iommu groups.
	 */
	if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY)) {
		iommu_group_put(iommu_group);
		return ERR_PTR(-EINVAL);
	}

	mutex_lock(&vfio.group_lock);
	group = vfio_group_find_from_iommu(iommu_group);
	if (group) {
		if (WARN_ON(vfio_group_has_device(group, dev)))
			group = ERR_PTR(-EINVAL);
		else
			refcount_inc(&group->drivers);
	} else {
		group = vfio_create_group(iommu_group, VFIO_IOMMU);
	}
	mutex_unlock(&vfio.group_lock);

	/* The vfio_group holds a reference to the iommu_group */
	iommu_group_put(iommu_group);
	return group;
}

int vfio_device_set_group(struct vfio_device *device,
			  enum vfio_group_type type)
{
	struct vfio_group *group;

	if (type == VFIO_IOMMU)
		group = vfio_group_find_or_alloc(device->dev);
	else
		group = vfio_noiommu_group_alloc(device->dev, type);

	if (IS_ERR(group))
		return PTR_ERR(group);

	/* Our reference on group is moved to the device */
	device->group = group;
	return 0;
}

void vfio_device_remove_group(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	struct iommu_group *iommu_group;

	if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
		iommu_group_remove_device(device->dev);

	/* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
	if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
		return;
	list_del(&group->vfio_next);

	/*
	 * We could concurrently probe another driver in the group that might
	 * race vfio_device_remove_group() with vfio_get_group(), so we have to
	 * ensure that the sysfs is all cleaned up under lock otherwise the
	 * cdev_device_add() will fail due to the name aready existing.
	 */
	cdev_device_del(&group->cdev, &group->dev);

	mutex_lock(&group->group_lock);
	/*
	 * These data structures all have paired operations that can only be
	 * undone when the caller holds a live reference on the device. Since
	 * all pairs must be undone these WARN_ON's indicate some caller did not
	 * properly hold the group reference.
	 */
	WARN_ON(!list_empty(&group->device_list));
	WARN_ON(group->notifier.head);

	/*
	 * Revoke all users of group->iommu_group. At this point we know there
	 * are no devices active because we are unplugging the last one. Setting
	 * iommu_group to NULL blocks all new users.
	 */
	if (group->container)
		vfio_group_detach_container(group);
	iommu_group = group->iommu_group;
	group->iommu_group = NULL;
	mutex_unlock(&group->group_lock);
	mutex_unlock(&vfio.group_lock);

	iommu_group_put(iommu_group);
	put_device(&group->dev);
}

void vfio_device_group_register(struct vfio_device *device)
{
	mutex_lock(&device->group->device_lock);
	list_add(&device->group_next, &device->group->device_list);
	mutex_unlock(&device->group->device_lock);
}

void vfio_device_group_unregister(struct vfio_device *device)
{
	mutex_lock(&device->group->device_lock);
	list_del(&device->group_next);
	mutex_unlock(&device->group->device_lock);
}

int vfio_device_group_use_iommu(struct vfio_device *device)
{
	struct vfio_group *group = device->group;
	int ret = 0;

	lockdep_assert_held(&group->group_lock);

	if (WARN_ON(!group->container))
		return -EINVAL;

	ret = vfio_group_use_container(group);
	if (ret)
		return ret;
	vfio_device_container_register(device);
	return 0;
}

void vfio_device_group_unuse_iommu(struct vfio_device *device)
{
	struct vfio_group *group = device->group;

	lockdep_assert_held(&group->group_lock);

	if (WARN_ON(!group->container))
		return;

	vfio_device_container_unregister(device);
	vfio_group_unuse_container(group);
}

bool vfio_device_has_container(struct vfio_device *device)
{
	return device->group->container;
}

/**
 * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
 * @file: VFIO group file
 *
 * The returned iommu_group is valid as long as a ref is held on the file. This
 * returns a reference on the group. This function is deprecated, only the SPAPR
 * path in kvm should call it.
 */
struct iommu_group *vfio_file_iommu_group(struct file *file)
{
	struct vfio_group *group = file->private_data;
	struct iommu_group *iommu_group = NULL;

	if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
		return NULL;

	if (!vfio_file_is_group(file))
		return NULL;

	mutex_lock(&group->group_lock);
	if (group->iommu_group) {
		iommu_group = group->iommu_group;
		iommu_group_ref_get(iommu_group);
	}
	mutex_unlock(&group->group_lock);
	return iommu_group;
}
EXPORT_SYMBOL_GPL(vfio_file_iommu_group);

/**
 * vfio_file_is_group - True if the file is usable with VFIO aPIS
 * @file: VFIO group file
 */
bool vfio_file_is_group(struct file *file)
{
	return file->f_op == &vfio_group_fops;
}
EXPORT_SYMBOL_GPL(vfio_file_is_group);

/**
 * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
 *        is always CPU cache coherent
 * @file: VFIO group file
 *
 * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
 * bit in DMA transactions. A return of false indicates that the user has
 * rights to access additional instructions such as wbinvd on x86.
 */
bool vfio_file_enforced_coherent(struct file *file)
{
	struct vfio_group *group = file->private_data;
	struct vfio_device *device;
	bool ret = true;

	if (!vfio_file_is_group(file))
		return true;

	/*
	 * If the device does not have IOMMU_CAP_ENFORCE_CACHE_COHERENCY then
	 * any domain later attached to it will also not support it. If the cap
	 * is set then the iommu_domain eventually attached to the device/group
	 * must use a domain with enforce_cache_coherency().
	 */
	mutex_lock(&group->device_lock);
	list_for_each_entry(device, &group->device_list, group_next) {
		if (!device_iommu_capable(device->dev,
					  IOMMU_CAP_ENFORCE_CACHE_COHERENCY)) {
			ret = false;
			break;
		}
	}
	mutex_unlock(&group->device_lock);
	return ret;
}
EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);

/**
 * vfio_file_set_kvm - Link a kvm with VFIO drivers
 * @file: VFIO group file
 * @kvm: KVM to link
 *
 * When a VFIO device is first opened the KVM will be available in
 * device->kvm if one was associated with the group.
 */
void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
{
	struct vfio_group *group = file->private_data;

	if (!vfio_file_is_group(file))
		return;

	mutex_lock(&group->group_lock);
	group->kvm = kvm;
	mutex_unlock(&group->group_lock);
}
EXPORT_SYMBOL_GPL(vfio_file_set_kvm);

/**
 * vfio_file_has_dev - True if the VFIO file is a handle for device
 * @file: VFIO file to check
 * @device: Device that must be part of the file
 *
 * Returns true if given file has permission to manipulate the given device.
 */
bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
{
	struct vfio_group *group = file->private_data;

	if (!vfio_file_is_group(file))
		return false;

	return group == device->group;
}
EXPORT_SYMBOL_GPL(vfio_file_has_dev);

static char *vfio_devnode(const struct device *dev, umode_t *mode)
{
	return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
}

int __init vfio_group_init(void)
{
	int ret;

	ida_init(&vfio.group_ida);
	mutex_init(&vfio.group_lock);
	INIT_LIST_HEAD(&vfio.group_list);

	ret = vfio_container_init();
	if (ret)
		return ret;

	/* /dev/vfio/$GROUP */
	vfio.class = class_create(THIS_MODULE, "vfio");
	if (IS_ERR(vfio.class)) {
		ret = PTR_ERR(vfio.class);
		goto err_group_class;
	}

	vfio.class->devnode = vfio_devnode;

	ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
	if (ret)
		goto err_alloc_chrdev;
	return 0;

err_alloc_chrdev:
	class_destroy(vfio.class);
	vfio.class = NULL;
err_group_class:
	vfio_container_cleanup();
	return ret;
}

void vfio_group_cleanup(void)
{
	WARN_ON(!list_empty(&vfio.group_list));
	ida_destroy(&vfio.group_ida);
	unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
	class_destroy(vfio.class);
	vfio.class = NULL;
	vfio_container_cleanup();
}